Sri Ramakrishna Engineering College

About: Sri Ramakrishna Engineering College is a based out in . It is known for research contribution in the topics: Computer science & Control theory. The organization has 1030 authors who have published 843 publications receiving 3822 citations.

Enhanced imperialist competitive algorithm based efficient reversible data hiding technique

Abstract: This paper presents a novel reversible data hiding into a Vector Quantization (VQ) and Side Match Vector Quantization (SMVQ) based compression image to embed high capacity secret bits and recover cover image after data extraction. For optimal embedding capacity and to achieve exact recovery of cover image, this paper uses Enhanced Imperialist Competitive Algorithm (EICA). The threshold value is determined by the fitness function contrast sensitivity in EICA in order to signify embedding rate of each region in a cover image based on the size of the secret message. During data hiding, the output size of code stream is preserved in hiding two secret bits into a single index value. Discrete Cosine Transform (DCT) and Burrows Wheeler Transform (BWT) is applied before quantization for exact recovery of cover image and to achieve high compression ratio. Excellent energy compaction is provided by DCT and BWT reorders the symbols according to their context. Thus the proposed method provides a novel technique to embed secret bits into the cover image and compresses the embedded image. The output will be in the form of code streams with preserved size. The experimental results show that the proposed technique achieves high embedding capacity and compression rate.

Radial Basis Function Network Dependent Exclusive Mutual Interpolation for Missing Value Imputation

Abstract: The success of data mining relies on the purity of the data set. Before performing the data mining, th e data has to be cleaned. An unprocessed data set may contain noisy or missing values which is a critical researc h issue in the pre-processing stage. Imputation methods are be ing used to solve the missing value problems. In th is proposed work, a machine learning based imputation method is proposed by using the mutual information by exclusively interpolating two different section of the same dataset. For designing the proposed model, a radial basis function based neural network has been used. The performance of the proposed algorithm has been measured with respect to different rate or percenta ge of missing values in the data set and the result s has been compared with existing simple and efficient imputat ion methods also. To evaluate the performance, the standard WDBC data set has been used. The proposed algorithm performs well and was able to impute the missing values even in the worst cases with more th an 50% of missing values. Instead of using simple q uality measure such as Mean Square Error (MSE) to evaluate the imputed data quality, in this study, the quali ty is measured in terms of classification performance. Th e results arrived were more significant and compara ble.

Fake Instagram Profile Identification and Classification using Machine Learning

Abstract: With the increase in Internet usage, Instagram is now considered a very important platform for advertising marketing and social interaction. It is used by millions of users but, some users tend to misuse the platform by creating false identities. In recent years though Internet is a boon, online social networks are susceptible to threats by cyber criminals and spammers. Moreover, the popularity of social media users is determined by followers and hence users resort to different wrong means to promote increased profile followers. Researchers has offered a lot of feasible solutions for social media applications. In this paper, the automatic detection of fake profiles has been proposed to identify fake Instagram profiles so that the social life of Instagram users is secure. The prediction of fake Instagram profiles is facilitated using supervised learning machine algorithms. Upon classification, fake profile IDs are stored in a data dictionary to further help the concerned authorities to take necessary actions against fraudulent social media profiles. Experimentation has been done to compare the classification algorithms used to train the dataset.

Rice Husk Templated Mesoporous ZnO Nanostructures for Ethanol Sensing at Room Temperature

Abstract: Mesoporous zinc oxide nanostructures are successfully synthesized via the sol-gel route by using a rice husk as the template for ethanol sensing at room temperature. The structure and morphology of the nanostructures are characterized by x-ray diffraction, scanning electron microscopy (SEM), transmission electron microscopy (TEM), and nitrogen adsorption–desorption analyses. The mechanism for the growth of zinc oxide nanostructures over the biotemplate is proposed. SEM and TEM observations also reveal the formation of spherical zinc oxide nanoparticles over the interwoven fibrous network. Multiple sized pores having pore diameter ranging from 10–40 nm is also evidenced from the pore size distribution plot. The larger surface area and porous nature of the material lead to high sensitivity (40.93% for 300 ppm of ethanol), quick response (42 s) and recovery (40 s) towards ethanol at 300 K. The porous nature of the interwoven fibre-like network affords mass transportation of ethanol vapor, which results in faster surface accessibility, and hence it acts as a potential candidate for ethanol sensing at room temperature.